"Apache Hive" matching MCP servers:

Connects LLM agents to Apache Atlas for searching, tracing lineage, and managing metadata. Read-only by default, with optional write mode for creating entities and classifications.

Shared knowledge graph for AI coding agents. Search, create, and link verified technical knowledge across 12 node types with trust scoring, demand signals, and auto-provisioning. Install: npx agent-hive-mcp

Search reusable technical experience from AI agents, inspect evidence and limitations, and discover public agent Trust Passports through seven anonymous read-only MCP tools. Apache-2.0 integrations, examples and documentation connect to the separately governed hosted Remnant service. Agent OAuth and Candy are separate surfaces.

Sovereign, encrypted, persistent memory for AI agents. Eight MCP tools — remember, recall, forget (GDPR Art. 17 erasure), share, governance. Anchored on COTI V2 mainnet. Apache-2.0.

Local-first personal memory for AI agents. Ships its own SQLite memory store, so it runs standalone: agents propose and recall confirmed memory, while only the human can confirm, from a separate CLI. Optionally uses the macOS Hive app for encrypted vaults. Also provides a shared board for coordinating several agents.

Gives language models a working connection to Apache Jena Fuseki: SPARQL queries and updates, whole named-graph reads and writes over the Graph Store Protocol, bulk RDF loading from a sandboxed directory, and dataset administration such as listing, creating, backing up and compacting datasets. Named graphs are also exposed as MCP resources, and a read-only mode hides the seven writing tools.

Historical geography for AI agents: 1,000+ polities with real GeoJSON borders, dynastic succession chains, events, cities and trade routes from 4500 BCE to today, each with cited academic sources and a confidence score. Wraps the free AtlasPI REST API (https://atlaspi.it) as 39 MCP tools — no API key required, Apache-2.0.

Open-source team memory layer for AI coding agents. Markdown-in-git, user/team/org hierarchy, MCP. Apache-2.0.

Context infrastructure for AI-assisted development — on-demand Obsidian vault access via MCP

Enables AI assistants to read and edit a spatial canvas board of notes, tasks and ideas through the running desktop app, creating, updating, linking, grouping and arranging nodes, importing files, focusing the view and undoing changes so edits appear instantly and stay reversible.

Tamper-evident local memory + governance MCP for Claude Code, Cursor and Codex. Free, Apache-2.0. Ships the Claude Code Seatbelt Kit.

A Stack Overflow for Claude Code agents — a shared pool of solved-problem fixes.An agent hits an error, calls ask_pool for ranked prior fixes; solves something new, calls post_solution. Semantic search + write-time content shield. Free, Apache-2.0.

Enables shared, persistent memory and coordination for Claude Code and Codex sessions through a visible crew of tmux workers and a local SQLite store.

Enables coding agents to record, recall, supersede, and trace temporal decisions with rationale using MCP tools.

Enables Claude Code agents and sub-agents to share a persistent, compiled memory of project state, decisions, tasks, and facts across sessions instead of re-reading transcripts. Provides token-efficient bootstrap, search, commit, leased task claiming, and task-specific context compilation so parallel agents can coordinate without clobbering each other.

Self-hosted AI workspace exposing semantic document search (RAG via Qdrant and Apache Tika), long-term user memories, and multi-provider AI chat as MCP tools and resources.

MCP server for personal and shared memory with full-text search (SQLite FTS5) and outcome tracking, compatible with any MCP agent like Claude Code, Cursor, and Codex CLI.

Open scientific knowledge MCP for AI agents. Three profiles: search (15 tools incl. find_evidence, compare_papers, explore_topic), publish (5 tools for direct submission with AI-assisted review), govern (20 tools for proposals, voting, methodology shaping).

An MCP server for multi-agent collaboration, providing team messaging and long-term semantic memory with trust-based access control and single-writer consistency.

A Claude Code plugin that runs a cheap, always-on model as an MCP server to accumulate knowledge of your codebase, so your agent can ask broad questions instead of re-reading files.